M. Scarpelli et al., COMPUTER-ASSISTED ANALYSIS OF MEDULLOBLASTOMA - A CYTOLOGIC STUDY, Analytical and quantitative cytology and histology, 19(5), 1997, pp. 387-392
OBJECTIVE: To explore data from a set of cases of medulloblastoma to s
ee whether quantitative image analysis might suggest evidence for the
existence of lower and higher grade lesions. STUDY DESIGN: Fourteen co
nsecutive cases of medulloblastoma were obtained. Smears were stained
with toluidine blue. For each case, 50 nuclei were measured and a numb
er of densitometric features extracted. RESULTS: The existence of two
subgroups of cases, identified as lower and higher grade groups, was s
uggested by a plot of the total optical density versus nuclear area. T
wo nuclear texture features-the number of pixels with the same optical
density value occurring consecutively in the nucleus and the proporti
on of pixels in the high optical density range-divided the cases into
the same subgroups. The use of a clustering algorithm established two
clusters that corresponded to that subgrouping except for one case. Di
scriminant analysis gave an identical classification, with the misplac
ed case having a borderline discriminant function score. An unsupervis
ed learning algorithm based on an adaptive distance metric formed two
clusters and assigned the borderline case to the low grade subgroup. T
he grouping obtained by quantitative analysis was only partly related
to the grade of nuclear atypia subjectively evaluated. CONCLUSION: In
our series of medulloblastomas, quantitative analysis provided a means
of detecting differences in the nuclear size and texture that allowed
the classification of cases into two subgroups.